Update Claude Code GitHub Workflow

[leogdion]

🤖 Installing Claude Code GitHub App

This PR adds a GitHub Actions workflow that enables Claude Code integration in our repository.

What is Claude Code?

Claude Code is an AI coding agent that can help with:

• Bug fixes and improvements
• Documentation updates
• Implementing new features
• Code reviews and suggestions
• Writing tests
• And more!

How it works

Once this PR is merged, we'll be able to interact with Claude by mentioning @claude in a pull request or issue comment.
Once the workflow is triggered, Claude will analyze the comment and surrounding context, and execute on the request in a GitHub action.

Important Notes

• This workflow won't take effect until this PR is merged
• @claude mentions won't work until after the merge is complete
• The workflow runs automatically whenever Claude is mentioned in PR or issue comments
• Claude gets access to the entire PR or issue context including files, diffs, and previous comments

Security

• Our Anthropic API key is securely stored as a GitHub Actions secret
• Only users with write access to the repository can trigger the workflow
• All Claude runs are stored in the GitHub Actions run history
• Claude's default tools are limited to reading/writing files and interacting with our repo by creating comments, branches, and commits.
• We can add more allowed tools by adding them to the workflow file like:

allowed_tools: Bash(npm install),Bash(npm run build),Bash(npm run lint),Bash(npm run test)

There's more information in the Claude Code action repo.

After merging this PR, let's try mentioning @claude in a comment on any PR to get started!

---

Perform an AI-assisted review on

Summary by CodeRabbit

• Chores
  • Enhanced code review automation to trigger on additional pull request events (ready for review and reopened states), alongside existing triggers.
  • Updated workflow configuration system for improved management and flexibility.

[coderabbitai]

📝 Walkthrough

Walkthrough

Two GitHub workflow files are updated: the code review workflow now includes additional PR event triggers and replaces natural language prompts with plugin-based configuration, while the main workflow updates documentation and clarifies optional parameters.

Changes

Cohort / File(s)	Summary
Code Review Workflow Configuration .github/workflows/claude-code-review.yml	Extended PR event triggers to include ready_for_review and reopened events. Replaced multi-line natural language review prompt with plugin-based configuration system (pluginMarketplaces, plugins, allowedBots). Updated prompt to code-review trigger path format. Removed claude_args configuration line.
Main Workflow Documentation .github/workflows/claude.yml	Updated guidance comments for claude_args with new URL reference. Removed active default value for claude_args and marked as optional with commented line. Minor whitespace adjustments.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Poem

🐰✨ Our workflows now dance with plugin grace,
More triggers caught, a faster pace,
Config refined, docs made clear—
The future of reviews is here! 🚀

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Title check	⚠️ Warning	The title 'Add Claude Code GitHub Workflow' is partially related to the changeset. It describes adding a workflow, but the actual changes involve modifying existing workflow files (claude-code-review.yml and claude.yml) rather than adding a new workflow. The PR primarily extends triggers, replaces prompt configuration with plugin-based setup, and makes documentation updates to two workflows.	Update the title to more accurately reflect the changes, such as 'Update Claude Code Review and Claude workflows with plugin configuration' or 'Extend Claude workflow triggers and add plugin-based configuration'.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch add-claude-github-actions-1770213199160

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

🤖 Fix all issues with AI agents

In @.github/workflows/claude.yml:
- Around line 46-49: Update the outdated Claude CLI link in the workflow
comment: replace the `https://code.claude.com/docs/en/cli-reference` URL with
the new official CLI reference
`https://docs.claude.com/en/docs/claude-code/cli-usage` in the claude_args
comment block (the commented lines showing "claude_args" and the two example
URLs) so the documentation link points to the current Claude Code CLI docs.

🧹 Nitpick comments (1)

.github/workflows/claude-code-review.yml (1)

39-45: Pin plugin marketplace to a specific git ref to reduce drift.
The plugin_marketplaces URL supports git refs; append a tag or commit hash (e.g., https://github.com/anthropics/claude-code.git#v1.0.0) to lock the plugin catalog to a stable version.

[coderabbitai]

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

🌐 Web query:

claude-code-action documentation usage.md github anthropics

💡 Result:

The official Anthropic Claude Code GitHub Action is anthropics/claude-code-action on GitHub, and its “Usage Guide” lives in the repo at docs/usage.md (same documentation set linked from the README / Marketplace listing). [2][3]

Key docs/usage.md / usage concepts (also reflected in Anthropic’s docs page):

• Add the action to a workflow and provide at least anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}. [1]
• Optionally pass:
  • prompt (free-text instructions or slash commands like /review) [1]
  • claude_args (CLI passthrough, e.g. --max-turns 5, --model ...) [1]

Minimal example (from Anthropic docs):

- uses: anthropics/claude-code-action@v1
  with:
    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
    prompt: "/review"
    claude_args: "--max-turns 5"

[1]

Sources: Anthropic documentation for Claude Code GitHub Actions [1], the anthropics/claude-code-action repo README (which links to the Usage Guide) [2], and the GitHub Marketplace listing for the official action (which links the same docs set) [3].

References:
[1] https://docs.anthropic.com/en/docs/claude-code/github-actions
[2] https://github.com/anthropics/claude-code-action
[3] https://github.com/marketplace/actions/claude-code-action-official

---

🌐 Web query:

claude-code-action claude_args configuration options

💡 Result:

claude_args in anthropics/claude-code-action@v1 is a passthrough string: you can provide any Claude Code CLI flags (single line or YAML multiline). Example: claude_args: "--max-turns 5 --model … --mcp-config …". [1]

Commonly-used claude_args flags (from the GitHub Actions docs):

• --max-turns <n>: limit conversation turns (docs note default is 10) [1]
• --model <model-id>: select the model [1]
• --mcp-config <path>: load an MCP config file [1]
• --allowed-tools <comma-separated>: allow specific tools [1]
• --debug: enable debug output [1]

Notes on configuration shape in v1:

• v1 unified “what to do” into prompt, and all CLI tuning into claude_args (e.g., model, max turns, tools, MCP config, system-prompt related settings). [1][2]

---

🌐 Web query:

code.claude.com CLI reference documentation

💡 Result:

The CLI reference for Claude Code (what used to be linked from code.claude.com) is now published on Claude Docs here: https://docs.claude.com/en/docs/claude-code/cli-usage. [1]

Related (non-interactive / automation “headless” usage, incl. -p/--print, --output-format, --resume): https://docs.claude.com/en/docs/claude-code/sdk/sdk-headless. [2]

---

Update the code.claude.com documentation link to point to the current location.

The GitHub link (https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md) is current. However, the second link (https://code.claude.com/docs/en/cli-reference) is outdated; it should be updated to https://docs.claude.com/en/docs/claude-code/cli-usage where the official Claude Code CLI reference is now published.

🤖 Prompt for AI Agents

In @.github/workflows/claude.yml around lines 46 - 49, Update the outdated
Claude CLI link in the workflow comment: replace the
`https://code.claude.com/docs/en/cli-reference` URL with the new official CLI
reference `https://docs.claude.com/en/docs/claude-code/cli-usage` in the
claude_args comment block (the commented lines showing "claude_args" and the two
example URLs) so the documentation link points to the current Claude Code CLI
docs.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 14.27%. Comparing base (cb27cef) to head (069fd54).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #235      +/-   ##
==========================================
- Coverage   14.33%   14.27%   -0.06%     
==========================================
  Files          67       67              
  Lines        7179     7179              
==========================================
- Hits         1029     1025       -4     
- Misses       6150     6154       +4     

Flag	Coverage Δ
spm	14.27% <ø> (-0.05%)	⬇️
swift-6.1-jammy	14.27% <ø> (ø)
swift-6.1-noble	14.27% <ø> (-0.02%)	⬇️
swift-6.2-jammy	14.27% <ø> (ø)
swift-6.2-jammynightly	14.27% <ø> (-0.05%)	⬇️
swift-6.2-noble	14.27% <ø> (-0.06%)	⬇️
swift-6.2-noblenightly	14.27% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.